Process Model Forecasting Datasets

This repository provides benchmark datasets for process model forecasting and directly-follows (DF) relation time series analysis. The data are organized into three levels: raw_logs (XES format)This directory contains the original event logs from publicly available process mining benchmarks, including BPI2017, BPI2019_1, Sepsis, and Hospital Billing. All logs are stored in the standard XES format. Each dataset is accompanied by its original DOI below. processed_logs (XES format)This directory contains pre-processed versions of the raw event logs in XES format. The pre-processing follows a three-stage pipeline:(1) variant filtering and case completion augmentation (including start and end activities),(2) temporal trimming to remove warm-up and burn-in periods, and(3) extraction of directly-follows (DF) relations and their aggregation for time series construction.The purpose of these steps is to reduce noise, stabilize temporal dynamics, and preserve the core process behavior for forecasting. A detailed description of the pre-processing procedure, parameter settings, and assumptions is provided in the corresponding research article (https://doi.org/10.1007/s44311-025-00031-7). time_series (Parquet format)This directory contains multivariate time series constructed from directly-follows (DF) relations extracted from the processed event logs. Each variable represents the daily aggregated frequency of a specific DF relation, resulting in multivariate DF-based time series suitable for sequence modeling and forecasting. All files are stored in Parquet format for efficient storage and large-scale processing. Included Benchmark Datasets Each of the three directories contains the following four widely used benchmark event logs: BPI 2017 – https://doi.org/10.4121/uuid:5f3067df-f10b-45da-b98b-86ae4c7a310b BPI 2019 (Part 1) – https://doi.org/10.4121/uuid:d06aff4b-79f0-45e6-8ec8-e19730c248f1 Sepsis – https://doi.org/10.4121/uuid:915d2bfb-7e84-49ad-a286-dc35f063a460 Hospital Billing – https://doi.org/10.4121/uuid:76c46b83-c930-4798-a1c9-4be94dfeb741 These datasets support research on: Process model forecasting Directly-follows dynamics and bottleneck evolution Multivariate time series modeling of business processes